# Assistant API Annotations

**URL:** <https://community.openai.com/t/assistant-api-annotations/730817>\
**Category:** API\
**Created:** [April 29, 2024, 3:37am UTC](https://community.openai.com/t/assistant-api-annotations/730817 "2024-04-29T03:37:14Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![TemplarRush](https://avatars.discourse-cdn.com/v4/letter/t/2acd7d/32.png) [@TemplarRush](https://community.openai.com/u/TemplarRush)\
**Post date:** [April 29, 2024, 3:37am UTC](https://community.openai.com/t/assistant-api-annotations/730817/1 "2024-04-29T03:37:14Z")

</div>

Can anyone explain what the start\_index and end\_index are for? They don’t appear to match the index locations of the quotes from within any file (if using file\_search).

In the annotation list, are they listed in chronological of where they appear in the assistant response text? Does the first entry in the annotations array correspond to the first instance in the content[0].text.value and so on?

Example:

```auto
"content": [
	{
		"type": "text",
		"text": {
			"value": "Lorem ipsum dolor sit amet?6:4+source?. Ut enim ad minim veniam?6:4+source?. Excepteur sint occaecat est laborum.?8:0+source?",
			"annotations": [
				{
					"type": "file_citation",
					"text": "?6:4+source?",
					"start_index": 632,
					"end_index": 694,
					"file_citation": {
						"file_id": "file-111111111111111111111111"
					}
				},
				{
					"type": "file_citation",
					"text": "?6:4+source?",
					"start_index": 1038,
					"end_index": 1100,
					"file_citation": {
						"file_id": "file-111111111111111111111111"
					}
				},
				{
					"type": "file_citation",
					"text": "?8:0+source?",
					"start_index": 1283,
					"end_index": 1326,
					"file_citation": {
						"file_id": "file-222222222222222222222222"
					}
				}
			]
		}
	}
]

```

Thanks!

---

<div class="post-metadata">

**Author:** ![nikunj](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/nikunj/32/222621_2.png) [@nikunj](https://community.openai.com/u/nikunj)\
**Post date:** [April 29, 2024, 5:14am UTC](https://community.openai.com/t/assistant-api-annotations/730817/2 "2024-04-29T05:14:18Z")

</div>

They represent the start and end index of the string to be replaced (`amet?6:4+source?`) in the response text generated (`text.value`).

---

<div class="post-metadata">

**Author:** ![TemplarRush](https://avatars.discourse-cdn.com/v4/letter/t/2acd7d/32.png) [@TemplarRush](https://community.openai.com/u/TemplarRush)\
**Post date:** [April 29, 2024, 2:14pm UTC](https://community.openai.com/t/assistant-api-annotations/730817/3 "2024-04-29T14:14:41Z")

</div>

Is there any way to prompt the assistant to return the location (page #, paragraph #, etc) from within a file from which the assistant “found” the answer to your prompt? Is there a timeline on when quotes are going to be added back to the v2 assistants?

Thanks.

---

<div class="post-metadata">

**Author:** ![nikunj](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/nikunj/32/222621_2.png) [@nikunj](https://community.openai.com/u/nikunj)\
**Post date:** [April 29, 2024, 11:53pm UTC](https://community.openai.com/t/assistant-api-annotations/730817/4 "2024-04-29T23:53:41Z")

</div>

Unfortunately, no there isn’t and I don’t have a timeline I can share for more granular citations at the moment.

---

<div class="post-metadata">

**Author:** ![nikunj](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/nikunj/32/222621_2.png) [@nikunj](https://community.openai.com/u/nikunj)\
**Post date:** [May 1, 2024, 6:51am UTC](https://community.openai.com/t/assistant-api-annotations/730817/5 "2024-05-01T06:51:23Z")

</div>

Closed on May 1, 2024, 6:51am UTC